Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real context beyond that: the content is study notes rather than official IYT material (useful for trust/attribution), and drawings are delivered as links rather than inline, which tells the agent to reach for get_figure to render them. It omits failure behaviour for unknown level/topic/section ids, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler, front-loading the return payload ('a theory article, or one section of it, as text') before the content inventory and the caveat about provenance. The trailing 'not official IYT text' clause is slightly compressed and reads as an afterthought, but it is informative rather than redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing the return value, and it does so well: text, rule, reason, tables, and drawing links. For a four-parameter read tool this is largely complete; the remaining gap is that it never says how to obtain valid level and topic ids, which the sibling list_levels/list_theory presumably supply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with lang, level, topic, and section each documented in the schema, so the baseline is 3. The description contributes only the phrase 'or one section of it', which lightly reinforces the section parameter; it adds nothing about id formats, the English fallback for untranslated text, or the relationship between level and topic beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states precisely what the tool returns: a full theory article or a single section, as text, containing the rule, the reason, tables, and links to drawings. The resource and content are unambiguous, but it never differentiates itself from the sibling tools list_theory and search_theory, so an agent must infer the boundary between 'read one article' and 'list/search articles'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance and no mention of alternatives, even though list_theory (discover topics) and search_theory (find by keyword) are obvious competing entry points. The only usage hint is implicit in 'or one section of it', which loosely maps to the optional section parameter but does not tell the agent when to request a whole article versus a section.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.